@inproceedings{giroh-etal-2025-syntact,
    title = "{\ensuremath{<}}{SYNTACT}{\ensuremath{>}}: Structuring Your Natural Language {SOP}s into Tailored Ambiguity-Resolved Code Templates",
    author = "Giroh, Sachin Kumar  and
      Ghosh, Pushpendu  and
      Jain, Aryan  and
      Paunikar, Harshal Giridhari  and
      Rastogi, Aditi  and
      Yenigalla, Promod  and
      Nediyanchath, Anish",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.163/",
    pages = "2367--2376",
    ISBN = "979-8-89176-333-3",
    abstract = "This paper introduces {\ensuremath{<}}SYNTACT{\ensuremath{>}}, a three-stage multi agent LLM framework designed to transform unstructured and ambiguous Standard Operating Procedure (SOP) into a structured plan and an executable code template. Unstructured SOPs{---}common across industries such as finance, retail, and logistics{---}frequently suffer from ambiguity, missing information, and inconsistency, all of which hinder automation. SYNTACT addresses this through: (1) a Clarifier module that disambiguate the SOP using large language models, internal knowledge base (RAG) and human-in-the-loop , (2) a Planner that converts refined natural language instructions into a structured plan of hierarchical task flows through function (API) tagging, conditional branches and human-in-the-loop check-points, and (3) an Implementor that generates executable code fragments or pseudocode templates. We evaluate SYNTACT on real-world SOPs and synthetic variants, demonstrating an 88.4{\%} end-to-end accuracy and a significant reduction in inconsistency compared to leading LLM baselines. Ablation studies highlight the necessity of each component, with performance dropping notably when modules are removed.Our findings show that structured multi-agent pipelines like SYNTACT can meaningfully improve consistency, reduce manual effort, and accelerate automation at scale."
}